Bobb Kim

See how 11 Customer Success challenges break the path from customer signal to verified outcome, and where current CS tools still leave coordination work.

Build and improve a Runbear agent from Claude Code, then keep the approved teammate connected to apps, triggers, Slack permissions, and run history for the whole team.

How Runbear turned one teammate's local CS skills into a shared, trigger-driven workflow with human decisions in Slack.

Support AI should not stop at explaining tickets. See how Runbear turns safe, repeatable fixes into Slack workflows with scoped permissions, approval, auto-resolve, and an audit trail.

Free trial abuse is not stopped by detection alone. See how AI credit farming exposed the need for an operator workflow that can verify, escalate, block, and audit.

Tables are the blind spot in RAG pipelines. We rebuilt how Notion and Confluence tables reach your LLM — from Markdown to self-describing header-value pairs — and improved answer accuracy by 20.6%.

Connecting Slack to an AI agent is easy. Making that data actually useful to an LLM is the hard part. We improved retrieval accuracy by 27% with three changes: thread-level document splitting, noise filtering, and markup cleanup.